Part of Advances in Neural Information Processing Systems 30 (NIPS 2017)
Behnam Neyshabur, Srinadh Bhojanapalli, David Mcallester, Nati Srebro
With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization, highlighting the importance of scale normalization, and making a connection between sharpness and PAC-Bayes theory. We then investigate how well the measures explain different observed phenomena.